Model trends: Championship, 12 Mar 2017

Regular readers will know that I churn out updated model predictions after every round of matches but I’m aware that there’s quite a lot of information in them and they can be difficult to track. I’m pretty keen to keep tabs on how well the model performs myself – not least because I’m constantly tinkering with it – so I’ve come up with a simple template that tracks how its assessment of each EFL club has evolved over the season.

The way it works is pretty simple: for pre-season and after every round of games it shows the results of my simulations for a specific club in terms of both:

  • How their average predicted final league position has changed (the solid line in the top chart)
  • How their predicted probability of ending up in each section of the table has changed (the coloured columns in the bottom chart)

The point of this is to show how the model’s assessment of a club’s prospects has changed after each round of games, but I also wanted some idea of how good a predictor it is. I’ve therefore added (as a dashed line) each club’s actual league position and briefly assessed (under each graphic) how well it’s predicted this so far.

I’m not expecting a 100% accuracy rate for a variety of reasons, including:

  • As Leicester recently reminded us, football is notoriously difficult to predict and the strongest team doesn’t always win
  • The rating system that drives the predictions can take a little while to adjust to sudden changes (e.g. a big tactical shift, replacing the manager or a lot of transfer activity)
  • While I’m pretty happy with the rating system and model, there’s limited data available in the lower leagues and therefore it may miss some subtleties in the way certain teams perform

Anyway, onto the graphics. There’s one for every team along with a brief summary and my view of how well the model’s predicted their fortunes.

Villa have been a mid-table side all season in the model’s eyes, thanks to the dismal way they exited the Premier League being factored into the pre-season assessment of 13th (which is pretty close to where they are now). During their poor start (the dipping dashed line) performances weren’t terrible so the predictions didn’t alter all that much and their recent resurgence has brought things back pretty much full circle. Their final fleeting hopes of a late play-off surge look to have been extinguished in late January as Steve Bruce struggled to turn their fortunes around.

Model performance: Pretty good right from the start

Barnsley were expected to finish in lower mid-table at the start of the season (not unusual for a side promoted via the play-offs) and the model hasn’t been all that impressed with their performances this season. In late November it looked as though their bubble might have burst, but their successful festive period has kept them in the top half of the table. Recent results have been less encouraging but they still have a decent chance of a top half finish and they may well be doing something that my data doesn’t pick up.

Model performance: Too pessimistic until January

Gary Rowett consistently defied the model during his spell at Birmingham – I really want him to get back into management to see if he can repeat the trick with a different set of players, as the extent to which their results outstripped performances was truly impressive. His sacking triggered an eye-watering collapse in results that ended up making the model look prescient, although we obviously can’t be sure that wouldn’t have happened anyway.

Model performance: Pessimistic at first, but adjusted quickly (perhaps with help)

The model correctly predicted Blackburn’s difficult season after their disappointing finish to the previous campaign and unfortunately there’s not been much evidence to sway it. A recent upturn in form has hugely boosted their survival hopes (see the drop in the red bars in March) and they look set to finish the season roughly where the model said they would beforehand.

Model performance: Pretty good right from the start

Brentford performed well last season – particularly up front – and were expected by the model to be an outside challenger for the play-offs this time around. However the defence hasn’t been anywhere near as impressive and a poor run saw their promotion prospects start to evaporate in November. Performances are ebbing at the moment and a top half finish would be an achievement at this point.

Model performance: Too optimistic until December

Brighton finished strongly last season and were an automatic promotion favourite right from the start. A bumpy start wasn’t sufficient to shake the model’s faith and since late October even finishing outside the top six has looked almost unthinkable.

Model performance: Pretty good right from the start

Having finished last season in relatively good shape, the model was expecting a solid mid-table finish from the Robins this time around. However after a bright start that seemed to bear this out, the wheels started to fall off in November and things have been going downhill ever since. Strangely the balance of chances created has remained relatively healthy during this bad run, so it’s tempting to conclude that the problem is psychological and/or that they’re only one tweak away from turning it around. It will be interesting to see what effect their potentially pivotal win at Wigan will have.

Model performance: Didn’t see the collapse coming and continued optimism is yet to be borne out by results

Burton looked sufficiently convincing in gaining promotion last season that the model expected them to steer clear of the relegation scrap. As the season’s gone on those margins have become finer thanks to some wasteful finishing and poor chance creation generally, but some better recent luck is keeping them out of the bottom three for now and they still look to have enough about them to avoid the drop.

Model performance: A bit too optimistic at first, but could end up getting the big question right

The extent of Cardiff’s poor start was sufficient to deflate the model’s pre-season prediction but it has remained consistently north of the Bluebirds’ league position and has been vindicated following their rehabilitation under Neil Warnock. While a top half finish may now prove a stretch, they’re aligning pretty well with expectations overall.

Model performance: Optimism looks to have been correct

Many were expecting a strong campaign from Derby but some hilariously wasteful finishing saw the model quickly revise its expectations downward. Recovering to challenge for the play-offs was always going to be a big ask and Steve McClaren hasn’t yet worked his magic despite a brief promising flourish towards the end of 2016. Performances are tailing off slightly and a rethink may be needed over the summer.

Model performance: Quickly adjusted after their poor start

Fulham’s attack alone was sufficiently impressive to suggest a play-off challenge in pre-season and an improving defence is increasingly making them a force to be reckoned with. Whether or not they can barge their way into the top six they look set to finish there or thereabouts, with the model having been consistently optimistic about their chances.

Model performance: Justifiably optimistic from the beginning

Huddersfield look to have underachieved last season based on some encouraging underlying performances, so the model tipped them as play-off outsiders this time around. The Terriers have exceeded even those expectations and look to be the only side capable of breaking the Newcastle-Brighton duopoly at the top of the table.

Model performance: Correct to be optimistic, but didn’t go far enough

Ipswich’s ongoing problems in attack led the model to predict a difficult season and a brush with relegation, but they’ve maintained a comfortable distance from the drop zone. Performances have remained concerning so it took until January before their points tally was sufficient for the model to start revising its assessment upwards.

Model performance: Too pessimistic

Garry Monk has exceeded all expectations this season, including those of the model which still rates Leeds as a mid-table side rather than a play-off challenger. Regardless of their true level, results have been good enough to give them a strong chance of remaining in the top six.

Model performance: Too pessimistic and ongoing scepticism yet to be justified

It wasn’t exactly controversial to make Newcastle favourites for the title, but the model was particularly bullish given how much their performances were already improving towards the end of last season. Even a shaky start wasn’t sufficient to move their predicted finish below second place and they’ve looked nailed on to go up since November.

Model performance: Pretty good right from the start

Even when they were riding high earlier in the season, the model wasn’t convinced of Norwich’s automatic promotion credentials, although even the pre-season prediction of 7th now looks a shade optimistic. The Canaries’ poor run thereafter saw them drop as low as 12th in the table but they always looked likely to recover some of that ground, even if the play-offs look unreachable. It’s not clear how the managerial change will affect the remainder of their campaign.

Model performance: Broadly correct, if a little optimistic

Forest were expected to finish in lower mid-table after a bumpy end to last season and that assessment hasn’t changed all that much. The chaos that has unfolded off the pitch isn’t within the scope of the model and the subsequent downturn in performances – which could still end up costing them their Championship status – has nudged the predictions downwards.

Model performance: Broadly correct, ignoring problems behind the scenes

A solid return to the Championship last season was expected to continue but the extent to which Preston have pushed on this year (despite a poor start) caught the model slightly by surprise. As this season’s worn on a top half finish has looked increasingly more likely to the point where it’s now all but certain.

Model performance: Slightly too pessimistic

The model expected a season of consolidation for QPR and maintained that they’d end up in lower mid-table despite a bright start. At the turn of the year the prediction looked to be spot on as Rangers continued to drop, but Ian Holloway has defied expectations and turned their fortunes around.

Model performance: Slightly too pessimistic, but lots has changed

There are always a few teams that openly defy the model and this season none have done so more than Reading. Expected to struggle against relegation, they’ve continued to get results despite performances remaining sluggish, so either they’re riding a lot of luck (for which there is some evidence, e.g. an unusually high number of penalties awarded) or they’re doing something that the data isn’t measuring properly (e.g. they may be far better organised than the average team). They’ve had a few bad results lately, so their response over the next few weeks could tell us a lot about what’s been going on.

Model performance: Didn’t see that coming and still in denial

Neil Warnock’s rescue act at Rotherham last season was achieved without improving the Millers’ poor underlying performances all that much and so the model was very down on them from the beginning. Unfortunately it’s been proved painfully correct, with relegation having looked a near-certainty as early as October and nailed on since late November.

Model performance: Unfortunately bang on

The model really likes Sheffield Wednesday and has had them pegged for a play-off finish all season (even during their slow start). They’ve underperformed slightly versus expectations but are consistently out-creating opponents and mostly getting the rewards.

Model performance: Pretty close, perhaps a shade optimistic

Wigan’s strong showing in getting promoted made the model optimistic that they could avoid a relegation battle but their early season performances saw that quickly revised downwards. Frustratingly the Latics’ recent performances have improved – their defence is actually rated among the division’s best – but results haven’t done likewise and a return to League 1 now looks worryingly likely.

Model performance: Adjusted quickly from initial over-optimistic prediction

The model’s had a soft spot for Wolves all season and still thinks they’re performing well enough to be in the top half. I still maintain that they should have given Walter Zenga more time based on how promisingly he’d started, but either way they’ve continued to perform relatively well without getting the results to match.

Model performance: Optimism hasn’t been justified